基于多路正则匹配方法的水利工程知识图谱构建  

Knowledge Graph Construction for Water Conservancy Projects based on Multiplex Regular Matching Method

作　　者：赵纪为 朱慧娈 李然 刘欣羽 姚华明 ZHAO Jiwei;ZHU Huibian;LI Ran;LIU Xinyu;YAO Huaming(Hubei Key Laboratory of Petroleum Geochemistry and Environment,Yangtze University,Wuhan 430100,China;Anhui Provincial Water Resources and Hydropower Survey and Design Institute Co.,Ltd.,Hefei 230088,China;China Yangtze Power Co.,Ltd.,Yichang 443000,China)

机构地区：[1]长江大学资源与环境学院油气地球化学与环境湖北省重点实验室,湖北武汉430100 [2]安徽省水利水电勘测设计研究总院股份有限公司,安徽合肥230088 [3]中国长江电力股份有限公司,湖北宜昌443000

出　　处：《水电与新能源》2024年第12期48-51,共4页Hydropower and New Energy

摘　　要：针对水利工程数据规模小、半结构化的特点,提出一种基于半结构化水利数据的知识图谱构建方法-多路正则匹配方法,该方法包括数据清洗、文本相似度计算、提取规则制定、多路正则匹配等步骤。以安徽省水利工程半结构化数据为例,进行水利工程实体、关系抽取。结果表明,相较于现有的方法,所提方法性能指标F1值提升了约16%。In response to the small scale and semi-structure characteristics of the knowledge data of water conservancy projects,a knowledge graph construction approach for the semi-structured water conservancy project data based on multiplex regular matching method is proposed.It includes various steps such as data cleaning,text similarity calculation,extraction rule formulation,and multiplex regular matching.Taking the semi-structured data of the water conservancy projects in Anhui Province as an example,entities and relationships of water conservancy projects are extracted.The results show that the proposed method improves the performance indicator F1 value by about 16%compared to existing methods.

关 键 词：知识图谱 水利工程 智慧水利 正则表达式 

分 类 号：TV737[水利工程—水利水电工程]